moved the files into peft folder

peft/README.md

@@ -0,0 +1,3 @@
+---
+license: mit
+---

peft/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

peft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4ffbe4f5fc56caab09655485f29d491fdb29258eb01a8fb4da05cf1e9f406a
+size 167832240

peft/handler.py

@@ -0,0 +1,49 @@
+from unsloth import FastLanguageModel
+from peft import PeftModel
+from peft import PeftConfig
+
+class EndpointHandler():
+    def __init__(self, path="."):
+        
+        model, tokenizer = FastLanguageModel.from_pretrained(
+            model_name = ".",
+            max_seq_length = 2048,
+            dtype = None,
+            load_in_4bit = True,
+        )     
+        model.config.use_cache = False
+        model.config.pad_token_id = model.config.eos_token_id
+        tokenizer.pad_token = tokenizer.eos_token
+        tokenizer.padding_side = "right"
+        
+        self.model = model
+        self.model.eval()
+        self.device_map = "cuda" # the device to load the model onto
+        self.tokenizer = tokenizer
+        
+
+    def __call__(self, data: any) -> any:
+        inputs = data.pop("inputs", data)
+        if len(inputs) == 0:
+            raise ValueError("prompt cannot be empty")
+        model_input = self.tokenizer(inputs, return_tensors="pt").to(self.device_map)
+        output = self.model.generate(input_ids=model_input["input_ids"].to(self.device_map),
+                                  use_cache=False,
+                                  temperature=0.1, top_k=1, top_p=1.0, repetition_penalty=1.4,
+                                  max_new_tokens=256,
+                                  do_sample=True,
+                                  pad_token_id=self.tokenizer.pad_token_id,
+                                  eos_token_id=self.tokenizer.eos_token_id,
+                                  num_beams=1,
+                                  num_return_sequences=1)
+        output = self.tokenizer.decode(output[0])
+        result = (output
+                .split(self.tokenizer.eos_token)[0]
+                .split("Response:")[1]
+                .strip()
+                .split("###")[0]
+                .replace("```json", "")
+                .replace("```", ""))
+
+        return {"response":result}
+

peft/requirements.txt

@@ -0,0 +1,7 @@
+torch==2.1.0
+transformers==4.37.2
+xformers
+bitsandbytes
+peft
+ipython
+unsloth @ git+https://github.com/unslothai/unsloth.git@e091bca34ad5df406a693685ea576366d79636f8

peft/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

peft/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

peft/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}